{"id":"https://openalex.org/W7166825536","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1432","title":"PhageBench: Can LLMs Understand Raw Bacteriophage Genomes?","display_name":"PhageBench: Can LLMs Understand Raw Bacteriophage Genomes?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166825536","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1432"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1432","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1432","pdf_url":"https://aclanthology.org/2026.findings-acl.1432.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1432.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139788369","display_name":"Yusen Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusen Hou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034040709","display_name":"Weicai Long","orcid":"https://orcid.org/0009-0009-3205-9537"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weicai Long","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139777240","display_name":"Haitao HU","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haitao HU","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139756385","display_name":"Houcheng su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Houcheng su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139850776","display_name":"Junning Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junning Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139757308","display_name":"Yanlin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanlin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88180113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28674","last_page":"28698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11016","display_name":"Monoclonal and Polyclonal Antibodies Research","score":0.0031999999191612005,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bacteriophage","display_name":"Bacteriophage","score":0.3321000039577484},{"id":"https://openalex.org/keywords/outbreak","display_name":"Outbreak","score":0.2671000063419342},{"id":"https://openalex.org/keywords/pandemic","display_name":"Pandemic","score":0.2597000002861023},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.22269999980926514}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4309000074863434},{"id":"https://openalex.org/C2776441376","wikidata":"https://www.wikidata.org/wiki/Q165028","display_name":"Bacteriophage","level":4,"score":0.3321000039577484},{"id":"https://openalex.org/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C150903083","wikidata":"https://www.wikidata.org/wiki/Q7108","display_name":"Biotechnology","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C116675565","wikidata":"https://www.wikidata.org/wiki/Q3241045","display_name":"Outbreak","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C89623803","wikidata":"https://www.wikidata.org/wiki/Q12184","display_name":"Pandemic","level":5,"score":0.2597000002861023},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.25200000405311584},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.22840000689029694},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.22269999980926514},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.21220000088214874}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1432","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1432","pdf_url":"https://aclanthology.org/2026.findings-acl.1432.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1432","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1432","pdf_url":"https://aclanthology.org/2026.findings-acl.1432.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.476729154586792}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166825536.pdf","grobid_xml":"https://content.openalex.org/works/W7166825536.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Bacteriophages,":[0],"often":[1],"referred":[2],"to":[3,46,67],"as":[4],"the":[5,9,63,74,140],"dark":[6],"matter":[7],"of":[8,25,76,98,142],"biosphere,":[10],"play":[11],"a":[12],"critical":[13],"role":[14],"in":[15,20,110,127],"regulating":[16],"microbial":[17],"ecosystems":[18],"and":[19,31,52,94,114,134],"antibiotic":[21],"alternatives.Thus,":[22],"accurate":[23],"interpretation":[24],"their":[26,44],"genomes":[27],"holds":[28],"significant":[29,125],"scientific":[30],"practical":[32],"value.While":[33],"general-purpose":[34],"Large":[35],"Language":[36],"Models":[37],"(LLMs)":[38],"excel":[39],"at":[40],"understanding":[41,71],"biological":[42,54,151],"texts,":[43],"ability":[45],"directly":[47],"interpret":[48],"raw":[49],"nucleotide":[50],"sequences":[51,152],"perform":[53],"reasoning":[55,104,129,148],"remains":[56],"underexplored.To":[57],"address":[58],"this,":[59],"we":[60],"introduce":[61],"PhageBench,":[62],"first":[64],"benchmark":[65],"designed":[66],"evaluate":[68],"phage":[69,111],"genome":[70],"by":[72],"mirroring":[73],"workflow":[75],"bioinformatics":[77],"experts.The":[78],"dataset":[79],"contains":[80],"5,600":[81],"high-quality":[82],"samples":[83],"covering":[84],"five":[85],"core":[86],"tasks":[87,130],"across":[88],"three":[89],"stages:":[90],"Screening,":[91],"Quality":[92],"Control,":[93],"Phenotype":[95],"Annotation.Our":[96],"evaluation":[97],"eight":[99],"LLMs":[100],"reveals":[101],"that":[102],"generalpurpose":[103],"models":[105,145],"significantly":[106],"outperform":[107],"random":[108],"baselines":[109],"contig":[112],"identification":[113],"host":[115],"prediction,":[116],"demonstrating":[117],"promising":[118],"potential":[119],"for":[120,150],"genomic":[121],"understanding.However,":[122],"they":[123],"exhibit":[124],"limitations":[126],"complex":[128],"involving":[131],"long-range":[132],"dependencies":[133],"fine-grained":[135],"functional":[136],"localization.These":[137],"findings":[138],"highlight":[139],"necessity":[141],"developing":[143],"next-generation":[144],"with":[146],"enhanced":[147],"capabilities":[149],"1":[153],".":[154]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
